© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83942
    Prev
    Next
    INDEX
    Explanations

    interrogative questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    L
    2.28
    S
    2.05
    R
    1.78
    ت
    1.75
    د
    1.74
    M
    1.66
    ৮
    1.55
    N
    1.55
    P
    1.54
    T
    1.52
    POSITIVE LOGITS
     څه
    1.37
     самого
    1.22
     começ
    1.21
    ν
    1.20
     contenuti
    1.17
     óptica
    1.16
     ciała
    1.13
     массива
    1.13
     différents
    1.11
     شرطونو
    1.08
    Activations Density 0.000%

    No Known Activations